Agent skill

Idea Discovery

by AI4Scientist in AI4Scientist/nano-scientist

Workflow 1: Full idea discovery pipeline. An agent skill from AI4Scientist/nano-scientist.

No licenceAuto-check: warningsResearch & Science

Install Idea Discovery

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add AI4Scientist/nano-scientist --skill idea-discovery -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install AI4Scientist/nano-scientist idea-discovery --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/AI4Scientist/nano-scientist.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/idea-discovery .claude/skills/idea-discovery && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
idea-discovery
GitHub stars
128
Used in
3 other repos
Token cost
~3.8k tokens
SKILL.md length
1,352 words
Files
1
Skills in repo
74
Repo updated
First seen
Licence
None found

At a glance

Workflow 1: Full idea discovery pipeline. An agent skill from AI4Scientist/nano-scientist.

  • Works in 9 steps: Load Research Brief (if available) → 5: Reference Paper Summary (when… → Literature Survey → …
  • User says 找idea全流程
  • SKILL.md covers Overview, Constants, Pipeline and Output Protocols, plus 2 more sections
  • Reaches arxiv.org

What it does

Idea Discovery is an agent skill from AI4Scientist/nano-scientist. Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.

Its SKILL.md is about 3.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Research & Science. It works with OpenAI and arXiv. The repository describes itself as: An autonomous research agent that turns a topic into a peer-reviewed technical report.

When your agent uses it

  • User says 找idea全流程
  • Idea discovery pipeline
  • Wants the complete idea exploration workflow

Example prompts

  • “找idea全流程”
  • “idea discovery pipeline”
  • “从零开始找方向”
  • “/idea-discovery”

Requirements

  • Pre-approved tools (allowed-tools): Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply

Workflow steps

9 steps, taken from the step headings in SKILL.md.

  1. Load Research Brief (if available)
  2. 5: Reference Paper Summary (when REF_PAPER is set)
  3. Literature Survey
  4. Idea Generation + Filtering + Pilots
  5. Deep Novelty Verification
  6. External Critical Review
  7. 5: Method Refinement + Experiment Planning
  8. Final Report
  9. 5: Write Compact Files (when COMPACT = true)

What it can do on your machine

Read from SKILL.md and the folder at commit 7132192. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(*)
    • Read
    • Write
    • Edit
    • Grep
    • Glob
    • WebSearch
    • WebFetch
    • Agent
    • Skill

    …and 2 more on the same allowed-tools line.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • arxiv.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Idea Discovery loads about 3.8k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 1,352 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~3.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: warnings

The automated check found patterns that need a careful read before installing.

  • WarningTells the agent its actions are pre-authorized / not to stop for confirmationSKILL.md:319
    t << 'EOF' > file`) to write in chunks. Do NOT ask the user for permission — just do it silently.
  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, Skill, mcp__codex__codex, mcp__c

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,352 words (~3,786 tokens).

“Orchestrate a complete idea discovery workflow for: $ARGUMENTS”

— opening of SKILL.md by AI4Scientist
name
idea-discovery
allowed-tools
Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply
argument-hint
research-direction

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/idea-discovery of AI4Scientist/nano-scientist.

Open the folder on GitHubat commit 7132192

Used in 3 other repositories

We found 7 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in AI4Scientist/nano-scientist, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Idea Discovery next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Idea Discovery compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Idea Discovery this skillAI4Scientist/nano-scientist1283 repos~3.8kAutomated safety check: WarnNone
Novelty CheckGRIND-Lab-Core/night_owl_research_agent106—~1kAutomated safety check: PassNone
Read arXiv Paperkarpathy/nanochat59k1 repos~494Automated safety check: PassMIT
Literature Reviewneflibata-feng/MyArxiv-Agent12620 repos~5.9kAutomated safety check: NotesMIT
Openalex Databaseneflibata-feng/MyArxiv-Agent12612 repos~3kAutomated safety check: PassCustom licence
Citation Verification GuideGalaxy-Dawn/claude-scholar5.7k2 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Novelty Check

    GRIND-Lab-Core/night_owl_research_agent

    Validates that a research idea is genuinely novel vs. An agent skill from GRIND-Lab-Core/night_owl_research_agent.

    106 GitHub stars~1k tokensUpdated 5 mo ago
    Research & ScienceAuto-check passed
  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    59k GitHub starsUsed in 1 repo~494 tokens
    Research & ScienceAuto-check passed
  • Literature Review

    neflibata-feng/MyArxiv-Agent

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.).

    126 GitHub starsUsed in 20 repos~5.9k tokens
    Research & ScienceAuto-check: notes
  • Openalex Database

    neflibata-feng/MyArxiv-Agent

    Query and analyze scholarly literature using the OpenAlex database.

    126 GitHub starsUsed in 12 repos~3k tokens
    Research & ScienceAuto-check passed
  • Citation Verification Guide

    Galaxy-Dawn/claude-scholar

    Reference guidance for checking every citation in academic writing against canonical sources such as DOI, arXiv, CrossRef and Semantic Scholar, to catch fake or wrong references.

    5.7k GitHub starsUsed in 2 repos~1.9k tokens
    Research & ScienceAuto-check passed
  • Citation Management

    K-Dense-AI/claude-scientific-writer

    Finds papers in OpenAlex, PubMed and Google Scholar, turns DOIs, PMIDs and arXiv IDs into clean BibTeX, and validates citations for a manuscript or thesis.

    2.4k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes

More from AI4Scientist/nano-scientist

All 74 skills in this repo
  • Formula Derivation

    AI4Scientist/nano-scientist

    Structures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a…

    128 GitHub starsUsed in 5 repos~2.3k tokens
    Auto-check passed
  • Paper Compile

    AI4Scientist/nano-scientist

    Compile LaTeX paper to PDF, fix errors, and verify output. An agent skill from AI4Scientist/nano-scientist.

    128 GitHub starsUsed in 5 repos~2.5k tokens
    Auto-check: notes
  • Paper Figure

    AI4Scientist/nano-scientist

    Generate publication-quality figures and tables from experiment results.

    128 GitHub starsUsed in 5 repos~2.9k tokens
    Auto-check: notes
  • Paper Navigator

    AI4Scientist/nano-scientist

    Find and read academic papers: disambiguate queries, discover papers (search, citation traversal, recommendations, arXiv monitoring, trending, GitHub search), evaluate (TLDR, citations, code, SOTA)…

    128 GitHub stars~7.7k tokensUpdated 4 mo ago
    Auto-check: notes
  • Proof Writer

    AI4Scientist/nano-scientist

    Writes rigorous mathematical proofs for ML/AI theory. An agent skill from AI4Scientist/nano-scientist.

    128 GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed
  • Ablation Planner

    AI4Scientist/nano-scientist

    A skill your agent uses when main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission.

    128 GitHub starsUsed in 4 repos~1.3k tokens
    Auto-check: notes

Works with

Questions about Idea Discovery

What does Idea Discovery do?

Workflow 1: Full idea discovery pipeline. An agent skill from AI4Scientist/nano-scientist. Idea Discovery is an agent skill from AI4Scientist/nano-scientist. Workflow 1: Full idea discovery pipeline.

When should I use Idea Discovery?

Idea Discovery fits situations like: user says 找idea全流程; idea discovery pipeline; wants the complete idea exploration workflow.

How do I install Idea Discovery in Claude Code?

Run `npx skills add AI4Scientist/nano-scientist --skill idea-discovery -a claude-code`. Or copy the skill folder (skills/idea-discovery in AI4Scientist/nano-scientist) into .claude/skills/idea-discovery in your project. Claude Code loads it when a task matches its description.

How do I install Idea Discovery in Codex?

Run `npx skills add AI4Scientist/nano-scientist --skill idea-discovery -a codex`. Or copy the skill folder (skills/idea-discovery in AI4Scientist/nano-scientist) into .agents/skills/idea-discovery in your project. Codex loads it when a task matches its description.

Can I use Idea Discovery in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add AI4Scientist/nano-scientist --skill idea-discovery -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/idea-discovery, .gemini/skills/idea-discovery, .github/skills/idea-discovery and .opencode/skills/idea-discovery in your project.

What does Idea Discovery need to run?

SKILL.md names no scripts, command-line tools or credentials: Idea Discovery is instructions for the agent only. Its frontmatter pre-approves these tools: Bash(*), Read, Write, Edit, Grep, Glob, WebSearch, WebFetch, Agent, Skill, mcp__codex__codex, mcp__codex__codex-reply.

Does Idea Discovery access the network?

SKILL.md names 1 domain. In commands or code: arxiv.org; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Idea Discovery safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): tells the agent its actions are pre-authorized / not to stop for confirmation. Read the flagged lines before installing; the check is not a guarantee either way.

What licence does Idea Discovery use?

No licence was found for Idea Discovery or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Idea Discovery use?

About 3.8k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Idea Discovery?

Skills that share tags, products or a category with Idea Discovery: Novelty Check (GRIND-Lab-Core/night_owl_research_agent, 106 stars), Read arXiv Paper (karpathy/nanochat, 59k stars), Literature Review (neflibata-feng/MyArxiv-Agent, 126 stars) and Openalex Database (neflibata-feng/MyArxiv-Agent, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Idea Discovery?

AI4Scientist (a GitHub organization) maintains it in AI4Scientist/nano-scientist, which has 128 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on June 3, 2026.

Source: AI4Scientist/nano-scientist on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.